Wojna, Z;
Ferrari, V;
Guadarrama, S;
Silberman, N;
Chen, LC;
Fathi, A;
Uijlings, J;
(2017)
The devil is in the decoder.
In:
Proceedings of the British Machine Vision Conference 2017, BMVC 2017.
(pp. pp. 1-13).
BMVA Press
Preview |
Text
paper010.pdf - Published Version Download (2MB) | Preview |
Abstract
Many machine vision applications require predictions for every pixel of the input image (for example semantic segmentation, boundary detection). Models for such problems usually consist of encoders which decreases spatial resolution while learning a high-dimensional representation, followed by decoders who recover the original input resolution and result in low-dimensional predictions. While encoders have been studied rigorously, relatively few studies address the decoder side. Therefore this paper presents an extensive comparison of a variety of decoders for a variety of pixel-wise prediction tasks. Our contributions are: (1) Decoders matter: we observe significant variance in results between different types of decoders on various problems. (2) We introduce a novel decoder: bilinear additive upsampling. (3) We introduce new residual-like connections for decoders. (4) We identify two decoder types which give a consistently high performance.
| Type: | Proceedings paper |
|---|---|
| Title: | The devil is in the decoder |
| Event: | The British Machine Vision Conference (BMVC) |
| ISBN-13: | 9781901725605 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.5244/c.31.10 |
| Publisher version: | https://dx.doi.org/10.5244/C.31.10 |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10102202 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
